Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of political commentary and skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Picker
    -0.15
    mayan
    -0.15
    lam
    -0.15
    iais
    -0.15
    urette
    -0.14
     Sez
    -0.14
     Hed
    -0.13
    udder
    -0.13
    osex
    -0.13
    اÙĨÙĩ
    -0.13
    POSITIVE LOGITS
     instead
    0.31
    instead
    0.27
    Instead
    0.27
     Instead
    0.26
     вмеÑģÑĤ
    0.20
     Nope
    0.18
    pars
    0.15
    .fi
    0.15
    quiv
    0.14
    WI
    0.14
    Act Density 0.155%

    No Known Activations